INDEX
    Explanations
    New Auto-Interp
    Negative Logits
     orange
    1.32
     yellow
    1.28
     golden
    1.23
    yellow
    1.20
    Yellow
    1.18
     Yellow
    1.17
    orange
    1.15
     Orange
    1.12
    Golden
    1.12
     yellowish
    1.11
    POSITIVE LOGITS
     black
    2.04
     blacks
    1.95
     Black
    1.93
    Black
    1.93
     BLACK
    1.92
     Blacks
    1.85
    black
    1.85
    1.81
    1.80
    1.78
    Act Density 0.144%

    No Known Activations